Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3370 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6526. Min Range: -3.6526
Max Act: 3.6526. Min Act: -0.1700
Data Index: 6718232 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6526. Min Range: -3.6526
Max Act: 3.5900. Min Act: -0.1700
Data Index: 880911 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6526. Min Range: -3.6526
Max Act: 3.5587. Min Act: -0.1700
Data Index: 5006488 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6526. Min Range: -3.6526
Max Act: 3.5587. Min Act: -0.1700
Data Index: 3724945 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6526. Min Range: -3.6526
Max Act: 3.4648. Min Act: -0.1700
Data Index: 1166089 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6526. Min Range: -3.6526
Max Act: 3.4491. Min Act: -0.1700
Data Index: 8079147 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6526. Min Range: -3.6526
Max Act: 3.4334. Min Act: -0.1700
Data Index: 7197102 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6526. Min Range: -3.6526
Max Act: 3.4491. Min Act: -0.1700
Data Index: 2144746 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6526. Min Range: -3.6526
Max Act: 3.4334. Min Act: -0.1700
Data Index: 5967668 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6526. Min Range: -3.6526
Max Act: 3.4334. Min Act: -0.1700
Data Index: 7136519 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6526. Min Range: -3.6526
Max Act: 3.4178. Min Act: -0.1700
Data Index: 7066520 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6526. Min Range: -3.6526
Max Act: 3.4178. Min Act: -0.1700
Data Index: 1529460 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6526. Min Range: -3.6526
Max Act: 3.3864. Min Act: -0.1700
Data Index: 3148483 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6526. Min Range: -3.6526
Max Act: 3.4021. Min Act: -0.1700
Data Index: 7171122 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6526. Min Range: -3.6526
Max Act: 3.4021. Min Act: -0.1700
Data Index: 8023502 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6526. Min Range: -3.6526
Max Act: 3.3864. Min Act: -0.1700
Data Index: 4239494 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6526. Min Range: -3.6526
Max Act: 3.4021. Min Act: -0.1700
Data Index: 4580139 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6526. Min Range: -3.6526
Max Act: 3.3864. Min Act: -0.1700
Data Index: 3195833 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6526. Min Range: -3.6526
Max Act: 3.3864. Min Act: -0.1700
Data Index: 8474202 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6526. Min Range: -3.6526
Max Act: 3.3707. Min Act: -0.1700
Data Index: 7272162 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19